CtrlK
BlogDocsLog inGet started
Tessl Logo

remove-ai-patterns

Remove AI-writing patterns ("AI-isms") from text using the avoid-ai-writing catalog (conorbronsdon/avoid-ai-writing). Use ONLY when the user explicitly asks to remove AI patterns / AI-isms, "make this sound less like AI", "de-AI this text", or invokes remove-ai-patterns by name. Supports detect-only audit, edit-in-place, voice profiles (casual / professional / technical / warm / blunt), and iterate-to-convergence. NOT for clarity/composition rules or formal technical-prose polish — use agent-style for that. Do not auto-trigger for ordinary writing or editing tasks.

68

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

67%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a well-structured thin-wrapper overview with executable detector/validator commands, a blocking validation checkpoint, and an explicit convergence feedback loop. Its main weaknesses are verbose over-explanation in the SKILL_DIR and technical-mode passages, and that the upstream/ tree it delegates the core catalog and edit workflow to is absent from the bundle.

Suggestions

Tighten the SKILL_DIR resolution block: drop the meta-commentary ('You already know this skill's directory', the Codex vs Claude Code plugin-root segment explanation) and keep just the two assignment examples plus the failure-mode rationale.

Trim the technical-mode disambiguation paragraph to the one concrete effect ('skips title-case-header') and a single sentence noting context mode ≠ voice profile; move the longer distinction into upstream/SKILL.md.

Ship the referenced upstream/ files (upstream/SKILL.md, upstream/detector/validate.js, upstream/detector/patterns.js, upstream/UPSTREAM-PIN) in the bundle, or the detector and validator commands will fail with MODULE_NOT_FOUND at runtime.

DimensionReasoningScore

Conciseness

The body is mostly efficient but carries stretches of over-explanation — the multi-line SKILL_DIR resolution commentary ('the plugin root already is the writing plugin, so there is no extra plugins/writing segment', 'You already know this skill's directory') and the lengthy technical-mode disambiguation paragraph — that go beyond the 'minor' trimming of a 4 and fit the 'could be tightened' anchor of 3.

3 / 5

Actionability

Provides concrete, executable commands ('node "$SKILL_DIR/scripts/detect.js" FILE technical', 'node "$SKILL_DIR/upstream/detector/validate.js" ORIGINAL REWRITTEN'), lists valid modes, and describes the JSON output schema, but stops short of fully copy-paste-ready coverage because the edit-in-place path is delegated to upstream/SKILL.md and SKILL_DIR requires setup judgment — matching the 'concrete code with minor gaps' anchor of 4 rather than a 5.

4 / 5

Workflow Clarity

Four clearly sequenced steps include an explicit blocking validation checkpoint (step 3 validator, 'Treat a failure as a blocking problem') and a feedback loop (convergence 'audit -> revise cycle... cap of 2 passes'), so the destructive/batch cap does not apply; it sits at 4 rather than 5 because the core edit workflow is delegated to the upstream file rather than enumerated inline.

4 / 5

Progressive Disclosure

The thin-wrapper overview is well-structured with clear sections and one-level-deep references that are explicitly signaled and described ('upstream/SKILL.md — the full pattern catalog, tiered word lists, and mode definitions'); however the bundle is missing the entire upstream/ tree it points to, a minor organization/packaging gap that keeps it at 4 rather than 5.

4 / 5

Total

15

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that concretely enumerates capabilities, supplies multiple natural trigger phrases with synonyms, and explicitly carves out its niche against a sibling skill. It cleanly answers both what the skill does and when to invoke it.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'detect-only audit', 'edit-in-place', 'voice profiles (casual / professional / technical / warm / blunt)', and 'iterate-to-convergence' — giving comprehensive coverage of the skill's capabilities, matching the score-5 anchor rather than the 'minor gaps' of a 4.

5 / 5

Completeness

Explicitly answers both what ('Remove AI-writing patterns... Supports detect-only audit, edit-in-place, voice profiles... iterate-to-convergence') and when ('Use ONLY when the user explicitly asks...'), with concrete trigger phrases and negative guidance, matching the score-5 anchor.

5 / 5

Trigger Term Quality

Includes natural phrases users would actually say with synonyms — 'remove AI patterns / AI-isms', 'make this sound less like AI', 'de-AI this text' — matching the comprehensive-synonyms anchor of 5 rather than the 'a few natural terms missing' of a 4.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (de-AI-ing text with voice profiles and a JS detector) and explicitly distinguishes itself from sibling 'agent-style' ('NOT for clarity/composition rules or formal technical-prose polish — use agent-style for that'), matching the minimal-conflict-risk anchor of 5.

5 / 5

Total

20

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
pchalasani/claude-code-tools
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.